i SSKJrJr SSKJr SSKJr SSKJrJ r J r J r J r J r JrJr SSKrSSKJr SSKJr SSKJr "S S \ 5r\"S S 55r"S S\5rg))ABCabstractmethod) dataclass)MappingProxyType)CallableDictListMapping NamedTupleOptionalTupleUnionN)enforcedmethod) CompileSpec)ExportedProgramc0\rSrSr%\\S'\\\S'Srg)DelegationSpec backend_id compile_specsN) __name__ __module__ __qualname____firstlineno__str__annotations__r r__static_attributes__rb/var/www/html/ai-image-ml/venv/lib/python3.13/site-packages/executorch/exir/backend/partitioner.pyrrsO $$rrc8\rSrSr%Sr\\S'\\\ 4\S'Sr g)PartitionResulta tagged_exported_program: the graph with nodes that intend to be delegated containing a "DelegationSpec" metadata partition_tags: A dictionary that will be used to keep track of the tags and it's corresponding DelegationSpec. The tag is defined by users and used in the node.meta. tagged_exported_programpartition_tagsrN) rrrr__doc__rrrrrrrrr r"r"s -,n,--rr"c <\rSrSrSr\"054S\\\\ \ \ 4\ 44Sjjr S\S\4Sjr\S\\\\ \ \ 4\ 44Sj5r\\S\S\4S j55rS \S\\\R2R4\\\R:R</\ 444S jrS r g ) Partitioner$a Defines a callable interface for partitioning an exported program for backend delegation. A partitioner implementation would receive an exported program, determine what portions of the it can be delegated to certain backend (though a partitioner can target multiple backends as well), and return the PartitionResult including: - the same input module with specific nodes in the input graph tagged for delegation - the "partition_tags" to indicate how the tag is mapped to Delegation Spec. The nodes that intend to be delegated must be tagged (by setting node.meta["delegation_tag"]) and this tag must be provided in the `partition_tags` dictionary mapping to an instance of DelegationSpec(backend_id, method_compilation_spec). Each tag must represent a distinct submodule that we intend on lowering and should be fully contained. For details on method_compilation_spec see the to_backend API, as these objects follow the same format. Args: exported_program: An ExportedProgram in Edge dialect to be partitioned for backend delegation. speccXlgN_spec)selfr*s r __init__Partitioner.__init__;s  rexported_programreturnc$URU5$r,) partitionr/r2s r __call__Partitioner.__call__As~~.//rcUR$r,r-)r/s r r*Partitioner.specDs zzrcg)a Returns the input exported program with newly created sub-Modules encapsulating specific portions of the input "tagged" for delegation. The specific implementation is free to decide how existing computation in the input exported program should be delegated to one or even more than one specific backends. The contract is stringent in that: * Each node that is intended to be delegated must be tagged * No change in the original input exported program (ExportedProgram) representation can take place other than adding sub-Modules for encapsulating existing portions of the input exported program and the associated metadata for tagging. Args: exported_program: An ExportedProgram in Edge dialect to be partitioned for backend delegation. Returns: PartitionResult: includes the tagged graph and the delegation spec to indicate what backend_id and compile_spec is used for each node and the tag created by the backend developers. Nrr6s r r5Partitioner.partitionHs. repc /S4$)a Returns a list of operator names that should not be decomposed. When these ops are registered and the `to_backend` is invoked through to_edge_transform_and_lower it will be guaranteed that the program that the backend receives will not have any of these ops decomposed. Returns: List[torch._ops.OpOverload]: a list of operator names that should not be decomposed. Optional[Callable[[torch.fx.Node], bool]]]: an optional callable, acting as a filter, that users can provide which will be called for each node in the graph that users can use as a filter for certain nodes that should be continued to be decomposed even though the op they correspond to is in the list returned by ops_to_not_decompose. Nr)r/r=s r ops_to_not_decompose Partitioner.ops_to_not_decomposeas"Dzrr-N)!rrrrr&rr rrintfloatboolobjectr0rr"r7propertyr*rrr5r r torch_ops OpOverloadr rfxNoder?rrrr r(r($s0?Or>ReCeT12F:; 00_0geCeT$9:FBC / o  .  tEJJ))*HXuxx}}ot>S5T,UU Vrr()abcrr dataclassesrtypesrtypingrrr r r r r rrF'executorch.exir.backend.backend_detailsr+executorch.exir.backend.compile_spec_schemar torch.exportrrr"r(rrr rRsX$!"TTT BC(%Z%  .. .N#Nr